@InProceedings{bansal-EtAl:2017:EACLshort,
  author    = {Bansal, Sameer  and  Kamper, Herman  and  Lopez, Adam  and  Goldwater, Sharon},
  title     = {Towards speech-to-text translation without speech recognition},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {474--479},
  abstract  = {We explore the problem of translating speech to text in low-resource scenarios
	where neither automatic speech recognition (ASR) nor machine translation (MT)
	are available, but we have training data in the form of audio paired with text
	translations. We present the first system for this problem applied to a
	realistic multi-speaker dataset, the CALLHOME Spanish-English speech
	translation corpus. Our approach uses un- supervised term discovery (UTD) to
	cluster repeated patterns in the audio, creating a pseudotext, which we pair
	with translations to create a parallel text and train a simple bag-of-words MT
	model. We identify the challenges faced by the system, finding that the
	difficulty of cross-speaker UTD results in low recall, but that our system is
	still able to correctly translate some content words in test data.},
  url       = {http://www.aclweb.org/anthology/E17-2076}
}